Learning Disentangled Representation in Object-Centric Models for Visual Dynamics Prediction via Transformers

Recent work has shown that object-centric representations can greatly help improve the accuracy of learning dynamics while also bringing interpretability. In this work, we take this idea one step further, ask the following question: "can learning disentangled representation further improve the accuracy of visual dynamics prediction in object-centric models?" While there has been some attempt to learn such disentangled representations for the case of static images \citep{nsb}, to the best of our knowledge, ours is the first work which tries to do this in a general setting for video, without making any specific assumptions about the kind of attributes that an object might have. The key building block of our architecture is the notion of a {\em block}, where several blocks together constitute an object. Each block is represented as a linear combination of a given number of learnable concept vectors, which is iteratively refined during the learning process. The blocks in our model are discovered in an unsupervised manner, by attending over object masks, in a style similar to discovery of slots \citep{slot_attention}, for learning a dense object-centric representation. We employ self-attention via transformers over the discovered blocks to predict the next state resulting in discovery of visual dynamics. We perform a series of experiments on several benchmark 2-D, and 3-D datasets demonstrating that our architecture (1) can discover semantically meaningful blocks (2) help improve accuracy of dynamics prediction compared to SOTA object-centric models (3) perform significantly better in OOD setting where the specific attribute combinations are not seen earlier during training. Our experiments highlight the importance discovery of disentangled representation for visual dynamics prediction.

Artifact-Tolerant Clustering-Guided Contrastive Embedding Learning for Ophthalmic Images

Ophthalmic images and derivatives such as the retinal nerve fiber layer (RNFL) thickness map are crucial for detecting and monitoring ophthalmic diseases (e.g., glaucoma). For computer-aided diagnosis of eye diseases, the key technique is to automatically extract meaningful features from ophthalmic images that can reveal the biomarkers (e.g., RNFL thinning patterns) linked to functional vision loss. However, representation learning from ophthalmic images that links structural retinal damage with human vision loss is non-trivial mostly due to large anatomical variations between patients. The task becomes even more challenging in the presence of image artifacts, which are common due to issues with image acquisition and automated segmentation. In this paper, we propose an artifact-tolerant unsupervised learning framework termed EyeLearn for learning representations of ophthalmic images. EyeLearn has an artifact correction module to learn representations that can best predict artifact-free ophthalmic images. In addition, EyeLearn adopts a clustering-guided contrastive learning strategy to explicitly capture the intra- and inter-image affinities. During training, images are dynamically organized in clusters to form contrastive samples in which images in the same or different clusters are encouraged to learn similar or dissimilar representations, respectively. To evaluate EyeLearn, we use the learned representations for visual field prediction and glaucoma detection using a real-world ophthalmic image dataset of glaucoma patients. Extensive experiments and comparisons with state-of-the-art methods verified the effectiveness of EyeLearn for learning optimal feature representations from ophthalmic images.

Deep Learning for Bias Detection: From Inception to Deployment

To create a more inclusive workplace, enterprises are actively investing in identifying and eliminating unconscious bias (e.g., gender, race, age, disability, elitism and religion) across their various functions. We propose a deep learning model with a transfer learning based language model to learn from manually tagged documents for automatically identifying bias in enterprise content. We first pretrain a deep learning-based language-model using Wikipedia, then fine tune the model with a large unlabelled data set related with various types of enterprise content. Finally, a linear layer followed by softmax layer is added at the end of the language model and the model is trained on a labelled bias dataset consisting of enterprise content. The trained model is thoroughly evaluated on independent datasets to ensure a general application. We present the proposed method and its deployment detail in a real-world application.

Towards an Interpretable Latent Space in Structured Models for Video Prediction

We focus on the task of future frame prediction in video governed by underlying physical dynamics. We work with models which are object-centric, i.e., explicitly work with object representations, and propagate a loss in the latent space. Specifically, our research builds on recent work by Kipf et al. \cite{kipf&al20}, which predicts the next state via contrastive learning of object interactions in a latent space using a Graph Neural Network. We argue that injecting explicit inductive bias in the model, in form of general physical laws, can help not only make the model more interpretable, but also improve the overall prediction of model. As a natural by-product, our model can learn feature maps which closely resemble actual object positions in the image, without having any explicit supervision about the object positions at the training time. In comparison with earlier works \cite{jaques&al20}, which assume a complete knowledge of the dynamics governing the motion in the form of a physics engine, we rely only on the knowledge of general physical laws, such as, world consists of objects, which have position and velocity. We propose an additional decoder based loss in the pixel space, imposed in a curriculum manner, to further refine the latent space predictions. Experiments in multiple different settings demonstrate that while Kipf et al. model is effective at capturing object interactions, our model can be significantly more effective at localising objects, resulting in improved performance in 3 out of 4 domains that we experiment with. Additionally, our model can learn highly intrepretable feature maps, resembling actual object positions.

COVID-19 detection using Residual Attention Network an Artificial Intelligence approach

Coronavirus Disease 2019 (COVID-19) is caused by the severe acute respiratory syndrome coronavirus 2 virus (SARS-CoV-2). The virus transmits rapidly, it has a basic reproductive number ($R_0$) of $2.2-2.7$. In March, 2020 the World Health Organization declared the COVID-19 outbreak a pandemic. Effective testing for COVID-19 is crucial to controlling the outbreak since infected patients can be quarantined. But the demand for testing outstrips the availability of test kits that use Reverse Transcription Polymerase Chain Reaction (RT-PCR). In this paper, we present a technique to detect COVID-19 using Artificial Intelligence. Our technique takes only a few seconds to detect the presence of the virus in a patient. We collected a dataset of chest X-ray images and trained several popular deep convolution neural network-based models (VGG, MobileNet, Xception, DenseNet, InceptionResNet) to classify chest X-rays. Unsatisfied with these models we then designed and built a Residual Attention Network that was able to detect COVID-19 with a testing accuracy of 98\% and a validation accuracy of 100\%. Feature maps of our model show which areas within a chest X-ray are important for classification. Our work can help to increase the adaptation of AI-assisted applications in clinical practice.

Lifted Marginal MAP Inference

Lifted inference reduces the complexity of inference in relational probabilistic models by identifying groups of constants (or atoms) which behave symmetric to each other. A number of techniques have been proposed in the literature for lifting marginal as well MAP inference. We present the first application of lifting rules for marginal-MAP (MMAP), an important inference problem in models having latent (random) variables. Our main contribution is two fold: (1) we define a new equivalence class of (logical) variables, called Single Occurrence for MAX (SOM), and show that solution lies at extreme with respect to the SOM variables, i.e., predicate groundings differing only in the instantiation of the SOM variables take the same truth value (2) we define a sub-class {\em SOM-R} (SOM Reduce) and exploit properties of extreme assignments to show that MMAP inference can be performed by reducing the domain of SOM-R variables to a single constant.We refer to our lifting technique as the {\em SOM-R} rule for lifted MMAP. Combined with existing rules such as decomposer and binomial, this results in a powerful framework for lifted MMAP. Experiments on three benchmark domains show significant gains in both time and memory compared to ground inference as well as lifted approaches not using SOM-R.